© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 206046
    Prev
    Next
    INDEX
    Explanations

    you . / claim , / rest of / cut the

    np_acts-logits-general · gemini-2.5-flash-lite

    rules, respect, and politeness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     której
    0.50
     ').
    0.50
    כב
    0.49
     yaptığı
    0.48
    ’).
    0.48
    जेंसी
    0.47
    څ
    0.47
    ').
    0.46
     kız
    0.46
     gelişt
    0.46
    POSITIVE LOGITS
    nel
    0.54
    number
    0.50
    nu
    0.50
    an
    0.45
    asparagus
    0.45
     संसाधनों
    0.45
    Resources
    0.45
     сен
    0.44
    es
    0.43
    은
    0.43
    Activations Density 0.001%

    No Known Activations